Instructions to use Undi95/MiquMaid-v2-70B-DPO-LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/MiquMaid-v2-70B-DPO-LoRA with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Undi95/MiquMaid-v2-70B-DPO-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/MiquMaid-v2-70B-DPO-LoRA")
model = AutoModelForCausalLM.from_pretrained("Undi95/MiquMaid-v2-70B-DPO-LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Undi95/MiquMaid-v2-70B-DPO-LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/MiquMaid-v2-70B-DPO-LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/MiquMaid-v2-70B-DPO-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Undi95/MiquMaid-v2-70B-DPO-LoRA

SGLang

How to use Undi95/MiquMaid-v2-70B-DPO-LoRA with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Undi95/MiquMaid-v2-70B-DPO-LoRA" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/MiquMaid-v2-70B-DPO-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Undi95/MiquMaid-v2-70B-DPO-LoRA" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/MiquMaid-v2-70B-DPO-LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Undi95/MiquMaid-v2-70B-DPO-LoRA with Docker Model Runner:
```
docker model run hf.co/Undi95/MiquMaid-v2-70B-DPO-LoRA
```

See axolotl config

axolotl version: 0.4.0

base_model: NeverSleep/MiquMaid-v2-70B
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

rl: dpo
datasets:
  - path: NobodyExistsOnTheInternet/ToxicDPOqa
    split: train
    type: chatml.alpaca
  - path: Undi95/toxic-dpo-v0.1-NoWarning
    split: train
    type: chatml.alpaca2
dataset_prepared_path:
val_set_size: 0.0
output_dir: ./out

adapter: qlora
lora_model_dir:

sequence_len: 1024
sample_packing: false
pad_to_sequence_len: true

lora_r: 16
lora_alpha: 8
lora_dropout: 0.05
lora_target_modules:
lora_target_linear: true
lora_fan_in_fan_out:

wandb_project: MiquMaidDPO
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 4
micro_batch_size: 3
num_epochs: 3
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.000001

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: true

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
eval_steps:
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: ./axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

out

This model is a fine-tuned version of NeverSleep/MiquMaid-v2-70B on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-06
train_batch_size: 3
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 3
gradient_accumulation_steps: 4
total_train_batch_size: 36
total_eval_batch_size: 24
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 598

Training results

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.16.1
Tokenizers 0.15.0

Downloads last month: 2

Model tree for Undi95/MiquMaid-v2-70B-DPO-LoRA

Base model

NeverSleep/MiquMaid-v2-70B

Quantized

(3)

this model